Machine learning for image classification is an active and rapidly developing field. With the proliferation of classifiers of different sizes and different architectures, the problem of choosing the right model becomes more and more important. While we can assess a model's classification accuracy statistically, our understanding of the way these models work is unfortunately quite limited. In order to gain insight into the decision-making process of different vision models, we propose using minimal sufficient pixels sets. These pixels capture the essence of an image through the lens of the model. By comparing position, overlap and size of sets of pixels, we identify that different architectures have statistically different minimal pixels sets, in both size and position. In particular, ConvNext and EVA models differ markedly from the others. We also identify that images which are misclassified are associated with statistically significant larger pixels sets than correct classifications.
论文检索
输入标题、作者或关键词，从 7,876 篇学术成果中精准定位
It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features.In this work, we propose "Amending Inherent Interpretability via Self-Supervised Masking" (AIM), a simple yet surprisingly effective method that promotes the network's utilization of genuine features over spurious alternatives without requiring additional annotations.In particular, AIM uses features at multiple encoding stages to guide a self-supervised, sample-specific feature-masking process. As a result, AIM allows training well-performing and inherently interpretable models that faithfully summarize the decision process.When tested on challenging datasets designed to assess reliance on spurious features and out-of-domain generalization, AIM networks demonstrate significant dual benefits: Evaluations show that AIM improves interpretability, as measured by the Energy Pointing Game (EPG) score, by ~6-37%, while simultaneously enhancing accuracy by ~10-40%. These impressive performance gains are further validated on the standard in-domain CUB-200 dataset for fine-grained classification. The results provide compelling evidence supporting our hypothesis that AIM finds genuine and meaningful features that directly contribute to its improved human interpretability.
While deep models are effectively trained based on a softmax cross-entropy loss, a cosine-based softmax loss also works for producing favorable feature embedding.In the cosine-based softmax, temperature plays a crucial role in properly scaling the logits of cosine similarities, though being manually tuned in ad-hoc ways as there is less prior knowledge about the temperature.In this paper, we address the challenging problem to adaptively estimate the temperature of cosine-based softmax in the framework of supervised image classification.By analyzing the cosine-based softmax representation from a geometrical viewpoint regarding features and classifiers, we construct a criterion in a least-square fashion which enables us to optimize the temperature at each sample via simple greedy search.Besides, our thorough analysis about temperature clarifies that feature embedding by the cosine-based softmax loss is endowed with diverse characteristics which are controllable by the temperature in an explainable way.The experimental results demonstrate that our optimized temperature contributes to determine a feasible range of temperature to control the feature characteristics and produces favorable performance on various image classification tasks.
Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD methods treat all samples uniformly, overlooking the varying learning value of each sample and thereby limiting effectiveness. In this paper, we propose Entropy-based Adaptive Knowledge Distillation (EA-KD), a simple yet effective plug-and-play KD method that prioritizes learning from valuable samples. EA-KD quantifies each sample's learning value by strategically combining the entropy of the teacher and student output, then dynamically reweights the distillation loss to place greater emphasis on high-entropy samples. Extensive experiments across diverse KD frameworks and tasks--including image classification, object detection, and large language model (LLM) distillation--demonstrate that EA-KD consistently enhances performance, achieving state-of-the-art results with negligible computational cost. Our code is available at: https://github.com/cpsu00/EA-KD
Connectionist temporal classification (CTC)-based scene text recognition (STR) methods, e.g., SVTR, are widely employed in OCR applications, mainly due to their simple architecture, which only contains a visual model and a CTC-aligned linear classifier, and therefore fast inference. However, they generally exhibit worse accuracy than encoder-decoder-based methods (EDTRs) due to struggling with text irregularity and linguistic missing. To address these challenges, we propose SVTRv2, a CTC model endowed with the ability to handle text irregularities and model linguistic context. First, a multi-size resizing strategy is proposed to resize text instances to appropriate predefined sizes, effectively avoiding severe text distortion. Meanwhile, we introduce a feature rearrangement module to ensure that visual features accommodate the requirement of CTC, thus alleviating the alignment puzzle. Second, we propose a semantic guidance module. It integrates linguistic context into the visual features, allowing CTC model to leverage language information for accuracy improvement. This module can be omitted at the inference stage and would not increase the time cost. We extensively evaluate SVTRv2 in both standard and recent challenging benchmarks, where SVTRv2 is fairly compared to popular STR models across multiple scenarios, including different types of text irregularity, languages, long text, and whether employing pretraining. SVTRv2 surpasses most EDTRs across the scenarios in terms of accuracy and inference speed. Code: https://github.com/Topdu/OpenOCR.
Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?
PDF ↗Self-supervised learning (SSL) has revolutionized representation learning in Remote Sensing (RS), advancing Geospatial Foundation Models (GFMs) to leverage vast unlabeled satellite imagery for diverse downstream tasks. Currently, GFMs primarily employ objectives like contrastive learning or masked image modeling, owing to their proven success in learning transferable representations. However, generative diffusion models, which demonstrate the potential to capture multi-grained semantics essential for RS tasks during image generation, remain underexplored for discriminative applications. This prompts the question: can generative diffusion models also excel and serve as GFMs with sufficient discriminative power? In this work, we answer this question with SatDiFuser, a framework that transforms a diffusion-based generative geospatial foundation model into a powerful pretraining tool for discriminative RS. By systematically analyzing multi-stage, noise-dependent diffusion features, we develop three fusion strategies to effectively leverage these diverse representations. Extensive experiments on remote sensing benchmarks show that SatDiFuser outperforms state-of-the-art GFMs, achieving gains of up to +5.7% mIoU in semantic segmentation and +7.9% F1-score in classification, demonstrating the capacity of diffusion-based generative foundation models to rival or exceed discriminative GFMs. The source code is available at: https://github.com/yurujaja/SatDiFuser.
We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to autoregressively predict future tokens. Our models are pre-trained on a diverse dataset of videos and images comprising over 1 trillion visual tokens. We explore different architectural, training, and inference design choices. We evaluate the learned visual representations on a range of downstream tasks including image recognition, video classification, object tracking, and robotics. Our results demonstrate that, despite minimal inductive biases, autoregressive pre-training leads to competitive performance across all benchmarks. Finally, we find that scaling our video models results in similar scaling curves to those seen in language models, albeit with a different rate.
While test-time adaptation (TTA) methods effectively address domain shifts by dynamically adapting pre-trained models to target domain data during online inference, their application to 3D point clouds is hindered by their irregular and unordered structure. Current 3D TTA methods often rely on computationally expensive spatial-domain optimizations and may require additional training data. In contrast, we propose Graph Spectral Domain Test-Time Adaptation (GSDTTA), a novel approach for 3D point cloud classification that shifts adaptation to the graph spectral domain, enabling more efficient adaptation by capturing global structural properties with fewer parameters. Point clouds in target domain are represented as outlier-aware graphs and transformed into graph spectral domain by Graph Fourier Transform (GFT). For efficiency, adaptation is performed by optimizing only the lowest 10% of frequency components, which capture the majority of the point cloud's energy. An inverse GFT (IGFT) is then applied to reconstruct the adapted point cloud with the graph spectral-driven point shift. This process is enhanced by an eigenmap-guided self-training strategy that iteratively refines both the spectral adjustments and the model parameters. Experimental results and ablation studies on benchmark datasets demonstrate the effectiveness of GSDTTA, outperforming existing TTA methods for 3D point cloud classification.
Facial expression datasets remain limited in scale due to privacy concerns, the subjectivity of annotations, and the labor-intensive nature of data collection. This limitation poses a significant challenge for developing modern deep learning-based facial expression analysis models, particularly foundation models, that rely on large-scale data for optimal performance. To tackle the overarching and complex challenge, we introduce SynFER (Synthesis of Facial Expressions with Refined Control), a novel framework for synthesizing facial expression image data based on high-level textual descriptions as well as more fine-grained and precise control through facial action units. To ensure the quality and reliability of the synthetic data, we propose a semantic guidance technique to steer the generation process and a pseudo-label generator to help rectify the facial expression labels for the synthetic images. To demonstrate the generation fidelity and the effectiveness of the synthetic data from SynFER, we conduct extensive experiments on representation learning using both synthetic data and real-world data. Results validate the efficacy of our approach and the synthetic data. Notably, our approach achieves a 67.23% classification accuracy on AffectNet when training solely with synthetic data equivalent to the AffectNet training set size, which increases to 69.84% when scaling up to five times the original size.
Mamba, an architecture with RNN-like sequence modeling of State Space Model (SSM), has demonstrated promising capabilities in long-range modeling with high efficiency. However, Mamba models struggle with structured 2D visual data using sequential computing, thereby lagging behind their attention-based counterparts. In this paper, we propose a Parallel Vision Mamba (PVMamba), a novel SSM architecture tailored for visual data. PVMamba encompasses two key designs: 1) Based on the sparsity and adjacency of visual signals, we parallelize the sequential computing through three core steps, termed Dynamic State Aggregation (DSA), i.e., parallelization, alignment, and aggregation. DSA generates the hidden state in SSM by a feasible spatial aggregation, thereby overcoming the inherent sequential constraints. 2) Along with maintaining linear computational complexity, we apply a dynamic operator to learn the spatial samplings for each hidden state. To further boost the local modeling capability, we restrict the dynamic operator to the neighboring pixels in shallow layers. We also devise a layer multiplexing technique to stabilize the training and reduce the learning redundancy. PVMamba is a versatile backbone network with dynamic operators for various vision tasks, such as image classification and dense prediction. Extensive experiments show that PVMamba achieves state-of-the-art performance on a range of benchmarks.
Information Pursuit (IP) is a recently introduced learning framework to construct classifiers that are interpretable-by-design. Given a set of task-relevant and interpretable data queries, IP selects a small subset of the most informative queries and makes predictions based on the gathered query-answer pairs. However, a key limitation of IP is its dependency on task-relevant interpretable queries, which typically require considerable data annotation and curation efforts. While previous approaches have explored using general-purpose large language models to generate these query sets, they rely on prompt engineering heuristics and often yield suboptimal query sets, resulting in a performance gap between IP and non-interpretable black-box predictors. In this work, we propose parameterizing IP queries as a learnable dictionary defined in the latent space of vision-language models such as CLIP. We formulate an optimization objective to learn IP queries and propose an alternating optimization algorithm that shares appealing connections with classic sparse dictionary learning algorithms. Our learned dictionary outperforms baseline methods based on handcrafted or prompted dictionaries across several image classification benchmarks.
Open-vocabulary multi-object tracking (OVMOT) represents a critical new challenge involving the detection and tracking of diverse object categories in videos, encompassing both seen categories (base classes) and unseen categories (novel classes). This issue amalgamates the complexities of open-vocabulary object detection (OVD) and multi-object tracking (MOT). Existing approaches to OVMOT often merge OVD and MOT methodologies as separate modules, not fully leveraging the video information. In this work, we propose VOVTrack, a novel method that integrates object states relevant to MOT and video-centric training to address this challenge from a video analysis standpoint. First, we consider the tracking-related state of the objects during tracking and propose a new prompt-guided attention mechanism for more accurate detection (localization and classification) of time-varying objects. Subsequently, we leverage raw video data without annotations for training by formulating a self-supervised object similarity learning technique to facilitate temporal object tracking (association). Experimental results underscore that VOVTrack establishes itself as a state-of-the-art solution for the open-vocabulary tracking task.
Spatial intelligence (SI) represents a cognitive ability encompassing the visualization, manipulation, and reasoning about spatial relationships, underpinning disciplines from neuroscience to robotics. We introduce SITE, a benchmark dataset towards SI Thorough Evaluation in a standardized format of multi-choice visual question-answering, designed to assess large vision-language models' spatial intelligence across diverse visual modalities (single-image, multi-image, and video) and SI factors (figural to environmental scales, spatial visualization and orientation, intrinsic and extrinsic, static and dynamic). Our approach to curating the benchmark combines a bottom-up survey of existing datasets and a top-down strategy drawing upon three classification systems in cognitive science, which prompt us to design two novel types of tasks about view-taking and dynamic scenes. Extensive experiments reveal that leading models fall behind human experts, especially in spatial orientation, a fundamental SI factor. Moreover, we demonstrate a positive correlation between a model's spatial reasoning proficiency and its performance on an embodied AI task.
Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal in the reasoning process. Specifically, process RMs evaluate each reasoning step, outcome RMs focus on the assessment of reasoning results, and critique RMs perform error analysis on the entire reasoning process, followed by corrections. However, existing benchmarks for vision-language RMs (VLRMs) typically assess only a single aspect of their capabilities (e.g., distinguishing between two answers), thus limiting the all-round evaluation and restricting the development of RMs in the visual-language domain. To address this gap, we propose a comprehensive and challenging benchmark, dubbed as VLRMBench, encompassing 12,634 questions. VLRMBench is constructed based on three distinct types of datasets, covering mathematical reasoning, hallucination understanding, and multi-image understanding. We design 12 tasks across three major categories, focusing on evaluating VLRMs in the aspects of process understanding, outcome judgment, and critique generation. Extensive experiments are conducted on 21 open-source models and 5 advanced closed-source models, highlighting the challenges posed by VLRMBench. For instance, in the `Forecasting Future', a binary classification task, the advanced GPT-4o achieves only a 76.0% accuracy. The code is available at https://github.com/JCruan519/VLRMBench.
Deep learning models are susceptible to backdoor attacks involving malicious perturbation of some training data with a trigger to force misclassification to a target class. Various triggers have been used including semantic triggers that are easily realizable. We present Prototype Guided Backdoor Defense (PGBD), a robust post-hoc defense that scales across different trigger types, including previously unsolved semantic triggers. PPGBD exploits displacements in the geometric spaces of activations to penalize movements towards the trigger. This is done using a novel sanitization loss of a post-hoc fine-tuning step. This approach scales to all types of attacks and triggers, and achieves better performance across settings. We also present the first defense against semantic attacks on a new celebrity face images dataset. Activation spaces can provide rich clues to enhance DL models in different ways.
OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM
PDF ↗Despite the remarkable progress of multimodal large language models (MLLMs), they continue to face challenges in achieving competitive performance on ordinal regression (OR; a.k.a. ordinal classification). To address this issue, this paper presents OrderChain, a novel and general prompting paradigm that improves the ordinal understanding ability of MLLMs by specificity and commonality modeling. Specifically, our OrderChain consists of a set of task-aware prompts to facilitate the specificity modeling of diverse OR tasks and a new range optimization Chain-of-Thought (RO-CoT), which learns a commonality way of thinking about OR tasks by uniformly decomposing them into multiple small-range optimization subtasks. Further, we propose a category recursive division (CRD) method to generate instruction candidate category prompts to support RO-CoT automatic optimization. Comprehensive experiments show that LLaVA model with our OrderChain improves baseline LLaVA significantly on diverse OR datasets, e.g., from 47.5% to 93.2% accuracy on the Adience dataset for age estimation, and from 30.0% to 85.7% accuracy on the Diabetic Retinopathy dataset. Notably, LLaVA with our OrderChain also remarkably outperforms state-of-the-art methods by 27% on accuracy and 0.24 on MAE on the Adience dataset. To our best knowledge, our OrderChain is the first work that augments MLLMs for OR tasks, and the effectiveness is witnessed across a spectrum of OR datasets. Project Page: https://order-chain.github.io/.
Efficient lightweight neural networks have received increasing attention due to their faster reasoning speed and easier deployment on mobile devices. However, existing video models still focus on the larger ViT architecture, and few works attempt to build efficient architecture. Since many efficient contrastive language-image pre-training (CLIP) models have shown strong zero-shot classification and retrieval capability, we attempt to fill the gap in video-text understanding models and propose a fast and efficient video-text model MobileViCLIP with strong zero-shot reasoning capability that can be deployed on mobile devices. In particular, our MobileViCLIP-Small obtains similar zero-shot retrieval performance as InternVideo2-L14 on text-to-video dataset MSR-VTT while being 46.7x faster when deployed on the mobile device. Furthermore, MobileViCLIP-Small can generalize to zero-shot action recognition task and obtains 1.0% better Top-1 accuracy than InternVideo2-S14 while being 5.6x faster on the mobile device. The code is available at https://github.com/MCG-NJU/MobileViCLIP.
PriorMotion: Generative Class-Agnostic Motion Prediction with Raster-Vector Motion Field Priors
PDF ↗Reliable spatial and motion perception is essential for safe autonomous navigation. Recently, class-agnostic motion prediction on bird's-eye view (BEV) cell grids derived from LiDAR point clouds has gained significant attention. However, existing frameworks typically perform cell classification and motion prediction on a per-pixel basis, neglecting important motion field priors such as rigidity constraints, temporal consistency, and future interactions between agents. These limitations lead to degraded performance, particularly in sparse and distant regions. To address these challenges, we introduce PriorMotion, an innovative generative framework designed for class-agnostic motion prediction that integrates essential motion priors by modeling them as distributions within a structured latent space. Specifically, our method captures structured motion priors using raster-vector representations and employs a variational autoencoder with distinct dynamic and static components to learn future motion distributions in the latent space. Experiments on the nuScenes dataset demonstrate that PriorMotion outperforms state-of-the-art methods across both traditional metrics and our newly proposed evaluation criteria. Notably, we achieve improvements of approximately 15.24% in accuracy for fast-moving objects, an 3.59% increase in generalization, a reduction of 0.0163 in motion stability, and a 31.52% reduction in prediction errors in distant regions. Further validation on FMCW LiDAR sensors confirms the robustness of our approach.
Intra-modal and Cross-modal Synchronization for Audio-visual Deepfake Detection and Temporal Localization
PDF ↗Recent deepfake detection algorithms focus solely on uni-modal or cross-modal inconsistencies. While the former disregards audio-visual correspondence entirely rendering them less effective against multimodal attacks, the latter overlooks inconsistencies in a particular modality. Moreover, many models are single-stage supervised frameworks, effective on specific training data but less generalizable to new manipulations. To address these gaps, we propose a two-stage multimodal framework that first learns intra-modal and cross-modal temporal synchronization on real videos, capturing audio-visual correspondences crucial for deepfake detection and localization. We introduce a Gaussian-targeted loss in our pretraining model to focus on learning relative synchronization patterns across multimodal pairs. Using pretrained features, our approach not only enables classification on fully manipulated videos but also supports a localization module for partial deepfakes with only specific segments spoofed. Moreover, the pretraining stage does not require fine-tuning, thus reducing complexity. Our model, tested on various benchmark datasets, demonstrates strong generalization and precise temporal localization.
Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts
PDF ↗Accurate monocular 3D object detection (M3OD) is pivotal for safety-critical applications like autonomous driving, yet its reliability deteriorates significantly under real-world domain shifts caused by environmental or sensor variations. To address these shifts, Test-Time Adaptation (TTA) methods have emerged, enabling models to adapt to target distributions during inference. While prior TTA approaches recognize the positive correlation between low uncertainty and high generalization ability, they fail to address the dual uncertainty inherent to M3OD: semantic uncertainty (ambiguous class predictions) and geometric uncertainty (unstable spatial localization). To bridge this gap, we propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD. Through a convex optimization lens, we introduce an innovative convex structure of the focal loss and further derive a novel conjugate loss, enabling label-agnostic uncertainty weighting and balanced learning for high-uncertainty objects. In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues, reducing uncertainty from the unstable 3D representation. This dual-branch mechanism forms a complementary loop: enhanced spatial perception improves semantic classification, and robust semantic predictions further refine spatial understanding. Extensive experiments demonstrate the superiority of DUO over existing methods across various datasets and domain shift types. The source code is available at https://github.com/hzcar/DUO.