Out-of-distribution (OOD) detection refers to training the model on in-distribution (ID) dataset to classify if the input images come from unknown classes. Considerable efforts have been invested in designing various OOD detection methods based on either convolutional neural networks or transformers. However, Zero-shot OOD detection methods driven by CLIP, which require only class names for ID, have received less attention. This paper presents a novel method, namely CLIP saying no (CLIPN), which empowers "no" logic within CLIP. Our key motivation is to equip CLIP with the capability of distinguishing OOD and ID samples via positive-semantic prompts and negation-semantic prompts. To be specific, we design a novel learnable "no" prompt and a "no" text encoder to capture the negation-semantic with images. Subsequently, we introduce two loss functions: the image-text binary-opposite loss and the text semantic-opposite loss, which we use to teach CLIPN to associate images with "no" prompts, thereby enabling it to identify unknown samples. Furthermore, we propose two threshold-free inference algorithms to perform OOD detection via using negation semantics from "no" prompts and text encoder. Experimental results on 9 benchmark datasets (3 ID datasets and 6 OOD datasets) for the OOD detection task demonstrate that CLIPN outperforms 7 well-used algorithms by at least 1.1% and 7.37% on AUROC and FPR95 on zero-shot OOD detection of ImageNet-1K. Our CLIPN can serve as a solid foundation for leveraging CLIP effectively in downstream OOD tasks.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. However, such models must be trained from scratch with specialised methods: therefore, access to a training dataset is required when the need for zero-shot classification arises. In this paper, we aim to equip pre-trained models with zero-shot classification capabilities without the use of image data. We achieve this with our proposed Image-free Classifier Injection with Semantics (ICIS) that injects classifiers for new, unseen classes into pre-trained classification models in a post-hoc fashion without relying on image data. Instead, the existing classifier weights and simple class-wise descriptors, such as class names or attributes, are used. ICIS has two encoder-decoder networks that learn to reconstruct classifier weights from descriptors (and vice versa), exploiting (cross-)reconstruction and cosine losses to regularise the decoding process. Notably, ICIS can be cheaply trained and applied directly on top of pre-trained classification models. Experiments on benchmark ZSL datasets show that ICIS produces unseen classifier weights that achieve strong (generalised) zero-shot classification performance. Code is available at https://github.com/ExplainableML/ImageFreeZSL.
Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement
PDF ↗In this paper, we develop a weakly supervised learning algorithm to learn robust semantic correspondences from large-scale datasets with only image-level labels. Following the spirit of multiple instance learning (MIL), we decompose the weakly supervised correspondence learning problem into three stages: image-level matching, region-level matching, and pixel-level matching. We propose a novel cascaded online correspondence refinement algorithm to integrate MIL and the correspondence filtering and refinement procedure into a single deep network and train this network end-to-end with only image-level supervision, i.e., without point-to-point matching information. During the correspondence learning process, pixel-to-pixel matching pairs inferred from weak supervision are propagated, filtered, and enhanced through masked correspondence voting and calibration. Besides, we design a correspondence consistency check algorithm to select images with discriminative key points to generate pseudo-labels for classical matching algorithms. Finally, we filter out about 110,000 images from the ImageNet ILSVRC training set to formulate a new dataset, called SC-ImageNet. Experiments on several popular benchmarks indicate that pre-training on SC-ImageNet can improve the performance of state-of-the-art algorithms efficiently. Our project is available on https://github.com/21210240056/SC-ImageNet.
We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO approaches which often study a known calibration within a single dataset, XVO efficiently learns to recover relative pose with real-world scale from visual scene semantics, i.e., without relying on any known camera parameters. We optimize the motion estimation model via self-training from large amounts of unconstrained and heterogeneous dash camera videos available on YouTube. Our key contribution is twofold. First, we empirically demonstrate the benefits of semi-supervised training for learning a general-purpose direct VO regression network. Second, we demonstrate multi-modal supervision, including segmentation, flow, depth, and audio auxiliary prediction tasks, to facilitate generalized representations for the VO task. Specifically, we find audio prediction task to significantly enhance the semi-supervised learning process while alleviating noisy pseudo-labels, particularly in highly dynamic and out-of-domain video data. Our proposed teacher network achieves state-of-the-art performance on the commonly used KITTI benchmark despite no multi-frame optimization or knowledge of camera parameters. Combined with the proposed semi-supervised step, XVO demonstrates off-the-shelf knowledge transfer across diverse conditions on KITTI, nuScenes, and Argoverse without fine-tuning.
Existing neural rendering methods for creating human avatars typically either require dense input signals such as video or multi-view images, or leverage a learned prior from large-scale specific 3D human datasets such that reconstruction can be performed with sparse-view inputs. Most of these methods fail to achieve realistic reconstruction when only a single image is available. To enable the data-efficient creation of realistic animatable 3D humans, we propose ELICIT, a novel method for learning human-specific neural radiance fields from a single image. Inspired by the fact that humans can effortlessly estimate the body geometry and imagine full-body clothing from a single image, we leverage two priors in ELICIT: 3D geometry prior and visual semantic prior. Specifically, ELICIT utilizes the 3D body shape geometry prior from a skinned vertex-based template model (i.e., SMPL) and implements the visual clothing semantic prior with the CLIP-based pretrained models. Both priors are used to jointly guide the optimization for creating plausible content in the invisible areas. Taking advantage of the CLIP models, ELICIT can use text descriptions to generate text-conditioned unseen regions. In order to further improve visual details, we propose a segmentation-based sampling strategy that locally refines different parts of the avatar. Comprehensive evaluations on multiple popular benchmarks, including ZJU-MoCAP, Human3.6M, and DeepFashion, show that ELICIT has outperformed strong baseline methods of avatar creation when only a single image is available. The code is public for research purposes at https://huangyangyi.github.io/ELICIT/.
We present a method for joint alignment of sparse in-the-wild image collections of an object category. Most prior works assume either ground-truth keypoint annotations or a large dataset of images of a single object category. However, neither of the above assumptions hold true for the long-tail of the objects present in the world. We present a self-supervised technique that directly optimizes on a sparse collection of images of a particular object/object category to obtain consistent dense correspondences across the collection. We use pairwise nearest neighbors obtained from deep features of a pre-trained vision transformer (ViT) model as noisy and sparse keypoint matches and make them dense and accurate matches by optimizing a neural network that jointly maps the image collection into a learned canonical grid. Experiments on CUB, SPair-71k and PF-Willow benchmarks demonstrate that our method can produce globally consistent and higher quality correspondences across the image collection when compared to existing self-supervised methods. Code and other material will be made available at https://kampta.github.io/asic.
Tracking both location and pose of multiple planar objects (MPOT) is of great significance to numerous real-world applications. The greater degree-of-freedom of planar objects compared with common objects makes MPOT far more challenging than well-studied object tracking, especially when occlusion occurs. To address this challenging task, we are inspired by amodal perception that humans jointly track visible and invisible parts of the target, and propose a tracking framework that unifies appearance perception and occlusion reasoning. Specifically, we present a dual-branch network to track the visible part of planar objects, including vertexes and mask. Then, we develop an occlusion area localization strategy to infer the invisible part, i.e., the occluded region, followed by a two-stream attention network finally refining the prediction. To alleviate the lack of data in this field, we build the first large-scale benchmark dataset, namely MPOT-3K. It consists of 3,717 planar objects from 356 videos and contains 148,896 frames together with 687,417 annotations. The collected planar objects have 9 motion patterns and the videos are shot in 6 types of indoor and outdoor scenes. Extensive experiments demonstrate the superiority of our proposed method on the newly developed MPOT-3K as well as other two popular single planar object tracking datasets. The code and MPOT-3K dataset are released on https://zzcheng.top/MPOT.
Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based methods have shown promising performance. Unlike previous methods that focus on sample storage or knowledge distillation against catastrophic forgetting, this paper aims to understand why the online learning models fail to generalize well from a new perspective of shortcut learning. We identify shortcut learning as the key limiting factor for online CL, where the learned features may be biased, not generalizable to new tasks, and may have an adverse impact on knowledge distillation. To tackle this issue, we present the online prototype learning (OnPro) framework for online CL. First, we propose online prototype equilibrium to learn representative features against shortcut learning and discriminative features to avoid class confusion, ultimately achieving an equilibrium status that separates all seen classes well while learning new classes. Second, with the feedback of online prototypes, we devise a novel adaptive prototypical feedback mechanism to sense the classes that are easily misclassified and then enhance their boundaries. Extensive experimental results on widely-used benchmark datasets demonstrate the superior performance of OnPro over the state-of-the-art baseline methods. Source code is available at https://github.com/weilllllls/OnPro.
The motivation of the semi-supervised domain adaptation (SSDA) is to train a model by leveraging knowledge acquired from the plentiful labeled source combined with extremely scarce labeled target data to achieve the lowest error on the unlabeled target data at the testing time. However, due to inter-domain and intra-domain discrepancies, the improvement of classification accuracy is limited. To solve these, we propose the Trico-training method that utilizes a multilayer perceptron (MLP) classifier and two graph convolutional network (GCN) classifiers called inter-view GCN and intra-view GCN classifiers. The first co-training strategy exploits a correlation between MLP and inter-view GCN classifiers to minimize the inter-domain discrepancy, in which the inter-view GCN classifier provides its pseudo labels to teach the MLP classifier, which encourages class representation alignment across domains. In contrast, the MLP classifier gives feedback to the inter-view GCN classifier by using a new concept, 'pseudo-edge', for neighbor's feature aggregation. Doing this increases the data structure mining ability of the inter-view GCN classifier; thus, the quality of generated pseudo labels is improved. The second co-training strategy between MLP and intra-view GCN is conducted in a similar way to reduce the intra-domain discrepancy by enhancing the correlation between labeled and unlabeled target data. Due to an imbalance in classification accuracy between inter-view and intra-view GCN classifiers, we propose the third co-training strategy that encourages them to cooperate to address this problem. We verify the effectiveness of the proposed method on three standard SSDA benchmark datasets: Office-31, Office-Home, and DomainNet. The extended experimental results show that our method surpasses the prior state-of-the-art approaches in SSDA.
In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively capture the rich semantics inside the video using the image encoder of CLIP. To tackle this, state-of-the-art methods adopt complex cross-modal modeling techniques to fuse the text information into video frame representations, which, however, incurs severe efficiency issues in large-scale retrieval systems as the video representations must be recomputed online for every text query. In this paper, we discard this problematic cross-modal fusion process and aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. Concretely, we first introduce a spatial-temporal "Prompt Cube" into the CLIP image encoder and iteratively switch it within the encoder layers to efficiently incorporate the global video semantics into frame representations. We then propose to apply an auxiliary video captioning objective to train the frame representations, which facilitates the learning of detailed video semantics by providing fine-grained guidance in the semantic space. With a naive temporal fusion strategy (i.e., mean-pooling) on the enhanced frame representations, we obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.
Deep Neural Networks (DNNs) have revolutionized visual classification tasks over the last decade. The training phase of deep-learning-based algorithms, however, often requires a vast amount of reliable annotated data. While reliability collecting such amount of labeled data usually yields to an exhaustive, expensive process, for many applications, acquiring massive datasets with imperfect annotations is straightforward. For instance, crawling search engines and online websites can generate a boatload amount of noisy labeled data. Hence, solving the problem of learning with noisy labels (LNL) is of paramount importance. Traditional LNL methods have successfully handled datasets with artificially injected noise, but they still fall short of adequately handling real-world noise. With the increasing use of meta-learning in the diverse fields of machine learning, researchers have tried to leverage auxiliary small clean datasets to meta-correct the training labels. Nonetheless, existing meta-label correction approaches are not fully exploiting their potential. In this study, we propose EMLC, an enhanced meta-label correction approach for the LNL problem. We re-examine the meta-learning process and introduce faster and more accurate meta-gradient derivations. We propose a novel teacher architecture tailored explicitly for the LNL problem, equipped with novel training objectives. EMLC outperforms prior approaches and achieves state-of-the-art results in all standard benchmarks. Notably, EMLC enhances the previous art on the noisy real-world dataset Clothing1M by 0.87%. Our publicly available code can be found at the following link: https://github.com/iccv23anonymous/Enhanced-Meta-Label-Correction
Lightness adaptation is vital to the success of image processing to avoid unexpected visual deterioration, which covers multiple aspects, e.g., low-light image enhancement, image retouching, and inverse tone mapping. Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability. To address this limitation, we propose a novel generalized lightness adaptation algorithm that extends conventional normalization techniques through a channel filtering design, dubbed Channel Selective Normalization (CSNorm). The proposed CSNorm purposely normalizes the statistics of lightness-relevant channels and keeps other channels unchanged, so as to improve feature generalization and discrimination. To optimize CSNorm, we propose an alternating training strategy that effectively identifies lightness-relevant channels. The model equipped with our CSNorm only needs to be trained on one lightness condition and can be well generalized to unknown lightness conditions. Experimental results on multiple benchmark datasets demonstrate the effectiveness of CSNorm in enhancing the generalization ability for the existing lightness adaptation methods. Code is available at https://github.com/mdyao/CSNorm.
Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. Existing methods such as data reweighing, resampling, and supervised contrastive learning enforce the class balance with a price of introducing imbalance between instances of head class and tail class, which may ignore the underlying rich semantic substructures of the former and exaggerate the biases in the latter. We overcome these drawbacks by a novel "subclass-balancing contrastive learning (SBCL)" approach that clusters each head class into multiple subclasses of similar sizes as the tail classes and enforce representations to capture the two-layer class hierarchy between the original classes and their subclasses. Since the clustering is conducted in the representation space and updated during the course of training, the subclass labels preserve the semantic substructures of head classes. Meanwhile, it does not overemphasize tail class samples, so each individual instance contribute to the representation learning equally. Hence, our method achieves both the instance- and subclass-balance, while the original class labels are also learned through contrastive learning among subclasses from different classes. We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance. In addition, we present extensive analyses and ablation studies of SBCL to verify its advantages.
We address the problem of out-of-distribution (OOD) detection for the task of object detection. We show that residual convolutional layers with batch normalisation produce Sensitivity-Aware FEatures (SAFE) that are consistently powerful for distinguishing in-distribution from out-of-distribution detections. We extract SAFE vectors for every detected object, and train a multilayer perceptron on the surrogate task of distinguishing adversarially perturbed from clean in-distribution examples. This circumvents the need for realistic OOD training data, computationally expensive generative models, or retraining of the base object detector. SAFE outperforms the state-of-the-art OOD object detectors on multiple benchmarks by large margins, e.g. reducing the FPR95 by an absolute 30.6% from 48.3% to 17.7% on the OpenImages dataset.
Referring image segmentation (RIS) aims to localize the object in an image referred by a natural language expression. Most previous studies learn RIS with a large-scale dataset containing segmentation labels, but they are costly. We present a weakly supervised learning method for RIS that only uses readily available image-text pairs. We first train a visual-linguistic model for image-text matching and extract a visual saliency map through Grad-CAM to identify the image regions corresponding to each word. However, we found two major problems with Grad-CAM. First, it lacks consideration of critical semantic relationships between words. We tackle this problem by modeling the relationship between words through intra-chunk and inter-chunk consistency. Second, Grad-CAM identifies only small regions of the referred object, leading to low recall. Therefore, we refine the localization maps with self-attention in Transformer and unsupervised object shape prior. On three popular benchmarks (RefCOCO, RefCOCO+, G-Ref), our method significantly outperforms recent comparable techniques. We also show that our method is applicable to various levels of supervision and obtains better performance than recent methods.
Despite advancements in user-guided video segmentation, extracting complex objects consistently for highly complex scenes is still a labor-intensive task, especially for production. It is not uncommon that a majority of frames need to be annotated. We introduce a novel semi-supervised video object segmentation (SSVOS) model, XMem++, that improves existing memory-based models, with a permanent memory module. Most existing methods focus on single frame annotations, while our approach can effectively handle multiple user-selected frames with varying appearances of the same object or region. Our method can extract highly consistent results while keeping the required number of frame annotations low. We further introduce an iterative and attention-based frame suggestion mechanism, which computes the next best frame for annotation. Our method is real-time and does not require retraining after each user input. We also introduce a new dataset, PUMaVOS, which covers new challenging use cases not found in previous benchmarks. We demonstrate SOTA performance on challenging (partial and multi-class) segmentation scenarios as well as long videos, while ensuring significantly fewer frame annotations than any existing method. Project page: https://max810.github.io/xmem2-project-page/
A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a less-explored topic. In this work, we first benchmark the performance of these models under different perturbations and datasets thereby representing real-world shifts, and highlight their degrading performance under these shifts. We then discuss on how complete model fine-tuning based existing robustification schemes might not be a scalable option given very large scale networks and can also lead them to forget some of the desired characterstics. Finally, we propose a simple and cost-effective method to solve this problem, inspired by knowledge transfer literature. It involves robustifying smaller models, at a lower computation cost, and then use them as teachers to tune a fraction of these large scale networks, reducing the overall computational overhead. We evaluate our proposed method under various vision perturbations including ImageNet-C,R,S,A datasets and also for transfer learning, zero-shot evaluation setups on different datasets. Benchmark results show that our method is able to induce robustness to these large scale models efficiently, requiring significantly lower time and also preserves the transfer learning, zero-shot properties of the original model which none of the existing methods are able to achieve.
Large Vision-Language Foundation Models (VLFM), such as CLIP, ALIGN and Florence, are trained on large private datasets of image-caption pairs and achieve superior transferability and robustness on downstream tasks, but they are difficult to use in many practical applications due to their large size, high latency and fixed architectures. Unfortunately, recent works show training a small custom VLFM for resource-limited applications is currently very difficult using public and smaller-scale data. In this paper, we introduce a new distillation mechanism (DIME-FM) that allows us to transfer the knowledge contained in large VLFMs to smaller, customized foundation models using a relatively small amount of inexpensive, unpaired images and sentences. We transfer the knowledge from the pre-trained CLIP-ViT-L/14 model to a ViT-B/32 model, with only 40M public images and 28.4M unpaired public sentences. The resulting model "Distill-ViT-B/32" rivals the CLIP-ViT-B/32 model pre-trained on its private WiT dataset (400M image-text pairs): Distill-ViT-B/32 achieves similar results in terms of zero-shot and linear-probing performance on both ImageNet and the ELEVATER (20 image classification tasks) benchmarks. It also displays comparable robustness when evaluated on five datasets with natural distribution shifts from ImageNet.
Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation
PDF ↗Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation. Early efforts focus on boosting the performance for only one task, e.g., fusion or segmentation, making it hard to reach `Best of Both Worlds'. To overcome this issue, in this paper, we propose a Multi-interactive Feature learning architecture for image fusion and segmentation, namely SegMiF, and exploit dual-task correlation to promote the performance of both tasks. The SegMiF is of a cascade structure, containing a fusion sub-network and a commonly used segmentation sub-network. By slickly bridging intermediate features between two components, the knowledge learned from the segmentation task can effectively assist the fusion task. Also, the benefited fusion network supports the segmentation one to perform more pretentiously. Besides, a hierarchical interactive attention block is established to ensure fine-grained mapping of all the vital information between two tasks, so that the modality/semantic features can be fully mutual-interactive. In addition, a dynamic weight factor is introduced to automatically adjust the corresponding weights of each task, which can balance the interactive feature correspondence and break through the limitation of laborious tuning. Furthermore, we construct a smart multi-wave binocular imaging system and collect a full-time multi-modality benchmark with 15 annotated pixel-level categories for image fusion and segmentation. Extensive experiments on several public datasets and our benchmark demonstrate that the proposed method outputs visually appealing fused images and perform averagely 7.66% higher segmentation mIoU in the real-world scene than the state-of-the-art approaches. The source code and benchmark are available at https://github.com/JinyuanLiu-CV/SegMiF.
Current referring video object segmentation (R-VOS) techniques extract conditional kernels from encoded (low-resolution) vision-language features to segment the decoded high-resolution features. We discovered that this causes significant feature drift, which the segmentation kernels struggle to perceive during the forward computation. This negatively affects the ability of segmentation kernels. To address the drift problem, we propose a Spectrum-guided Multi-granularity (SgMg) approach, which performs direct segmentation on the encoded features and employs visual details to further optimize the masks. In addition, we propose Spectrum-guided Cross-modal Fusion (SCF) to perform intra-frame global interactions in the spectral domain for effective multimodal representation. Finally, we extend SgMg to perform multi-object R-VOS, a new paradigm that enables simultaneous segmentation of multiple referred objects in a video. This not only makes R-VOS faster, but also more practical. Extensive experiments show that SgMg achieves state-of-the-art performance on four video benchmark datasets, outperforming the nearest competitor by 2.8% points on Ref-YouTube-VOS. Our extended SgMg enables multi-object R-VOS, runs about 3 times faster while maintaining satisfactory performance. Code is available at https://github.com/bo-miao/SgMg.