论文检索

Lijun Sheng, Jian Liang, Zilei Wang, Ran He

Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and the common practice of selecting from a limited set of open-source models, VLMs suffer from a higher risk of adversarial attacks than traditional vision models. Existing defense techniques typically rely on adversarial fine-tuning during training, which requires labeled data and lacks of flexibility for downstream tasks. To address these limitations, we propose robust test-time prompt tuning (R-TPT), which mitigates the impact of adversarial attacks during the inference stage. We first reformulate the classic marginal entropy objective by eliminating the term that introduces conflicts under adversarial conditions, retaining only the pointwise entropy minimization. Furthermore, we introduce a plug-and-play reliability-based weighted ensembling strategy, which aggregates useful information from reliable augmented views to strengthen the defense. R-TPT enhances defense against adversarial attacks without requiring labeled training data while offering high flexibility for inference tasks. Extensive experiments on widely used benchmarks with various attacks demonstrate the effectiveness of R-TPT.

Jiahua Rao, Hanjing Lin, Leyu Chen, Jiancong Xie, Shuangjia Zheng, Yuedong Yang

Phenotypic drug discovery presents a promising strategy for identifying first-in-class drugs by bypassing the need for specific drug targets. Recent advances in cell-based phenotypic screening tools, including Cell Painting and the LINCS L1000, provide essential cellular data that capture biological responses to compounds. While the integration of the multi-modal data enhances the use of contrastive learning (CL) methods for molecular phenotypic representation, these approaches treat all negative pairs equally, failing to discriminate molecules with similar phenotypes. To address these challenges, we introduce a foundational framework MINER that dynamically estimates the likelihoods of sample pairs as negative pairs based on uni-modal disentangled representations. In addition, our approach incorporates a mixture fusion strategy to effectively integrate multimodal data, even in cases where certain modalities are missing. Extensive experiments demonstrate that our method enhances both molecular property prediction and molecule-phenotype retrieval accuracy. Moreover, it successfully recommends drug candidates from phenotype for complex diseases documented in the literature. These findings underscore MINER's potential to advance drug discovery by enabling deeper insights into disease mechanisms and improving drug candidate recommendations.

Ziyang Wang, Shoubin Yu, Elias Stengel-Eskin, Jaehong Yoon, Feng Cheng, Gedas Bertasius, Mohit Bansal

Long-form video understanding has been a challenging task due to the high redundancy in video data and the abundance of query-irrelevant information. To tackle this challenge, we propose VideoTree, a training-free framework which builds a query-adaptive and hierarchical video representation for LLM reasoning over long-form videos. First, VideoTree extracts query-relevant information from the input video through an iterative process, progressively refining the selection of keyframes based on their relevance to the query. Furthermore, VideoTree leverages the inherent hierarchical structure of long video data, which is often overlooked by existing LLM-based methods. Specifically, we incorporate multi-granularity information into a tree-based representation, allowing VideoTree to extract query-relevant details from long videos in a coarse-to-fine manner. This enables the model to effectively handle a wide range of video queries with varying levels of detail. Finally, VideoTree aggregates the hierarchical query-relevant information within the tree structure and feeds it into an LLM reasoning model to answer the query. Our experiments show that VideoTree improves both reasoning accuracy and efficiency compared to existing methods. Specifically, VideoTree outperforms the existing training-free approaches on the popular EgoSchema and NExT-QA benchmarks with less inference time, achieving 61.1% and 75.6% accuracy on the test set without additional video-specific training. Moreover, on the long split of Video-MME benchmark (average 44 minutes), the training-free VideoTree framework achieves better performance than the strong proprietary GPT-4V model and many other MLLMs that were extensively trained on video data. Our code is provided in the supplementary materials and will be made public.

Jingyi Tian, Le Wang, Sanping Zhou, Sen Wang, Jiayi Li, Haowen Sun, Wei Tang

Robotic manipulation based on visual observations and natural language instructions is a long-standing challenge in robotics. Yet prevailing approaches model action distribution by adopting explicit or implicit representations, which often struggle to achieve a trade-off between accuracy and efficiency. In response, we propose PDFactor, a novel framework that models action distribution with a hybrid triplane representation. In particular, PDFactor decomposes 3D point cloud into three orthogonal feature planes and leverages a tri-perspective view transformer to produce dense cubic features as a latent diffusion field aligned with observation space representing 6-DoF action probability distribution at an arbitrary location. We employ a small denoising network conceptually as both a parameterized loss function measuring the quality of the learned latent features and an action gradient decoder to sample actions from the latent diffusion field during inference. This design enables our PDFactor to benefit from spatial awareness of explicit representation and arbitrary resolution of implicit representation, rendering it with manipulation accuracy, inference efficiency, and model scalability. Experiments demonstrate that PDFactor outperforms state-of-the-art approaches across a diverse range of manipulation tasks in RLBench simulation. Moreover, PDFactor can effectively learn multi-task policies from a limited number of human demonstrations, achieving promising accuracy in a variety of real-world manipulation tasks.

Guoyu Yang, Yuan Wang, Daming Shi, Yanzhong Wang

Recent real-time semantic segmentation models, whether single-branch or multi-branch, achieve good performance and speed. However, their speed is limited by multi-path blocks, and some depend on high-performance teacher models for training. To overcome these issues, we propose Golden Cudgel Network (GCNet). Specifically, GCNet uses vertical multi-convolutions and horizontal multi-paths for training, which are reparameterized into a single convolution for inference, optimizing both performance and speed. This design allows GCNet to self-enlarge during training and self-contract during inference, effectively becoming a "teacher model" without needing external ones. Experimental results show that GCNet outperforms existing state-of-the-art models in terms of performance and speed on the Cityscapes, CamVid, and Pascal VOC 2012 datasets. The code is available at https://github.com/gyyang23/GCNet.

Shun Iwase, Muhammad Zubair Irshad, Katherine Liu, Vitor Guizilini, Robert Lee, Takuya Ikeda, Ayako Amma, Koichi Nishiwaki, Kris Kitani, Rares Ambrus 等

Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions. To address these issues, we introduce ZeroGrasp, a novel framework that simultaneously performs 3D reconstruction and grasp pose prediction in near real-time. A key insight of our method is that occlusion reasoning and modeling the spatial relationships between objects is beneficial for both accurate reconstruction and grasping. We couple our method with a novel large-scale synthetic dataset, which comprises 1M photo-realistic images, high-resolution 3D reconstructions and 11.3B physically-valid grasp pose annotations for 12K objects from the Objaverse-LVIS dataset. We evaluate ZeroGrasp on the GraspNet-1B benchmark as well as through real-world robot experiments. ZeroGrasp achieves state-of-the-art performance and generalizes to novel real-world objects by leveraging synthetic data.

Jiong Lin, Lechen Zhang, Kwansoo Lee, Jialong Ning, Judah Goldfeder, Hod Lipson

Robot description models are essential for simulation and control, yet their creation often requires significant manual effort. To streamline this modeling process, we introduce AutoURDF, an unsupervised approach for constructing description files for unseen robots from point cloud frames. Our method leverages a cluster-based point cloud registration model that tracks the 6-DoF transformations of point clusters. Through analyzing cluster movements, we hierarchically address the following challenges: (1) moving part segmentation, (2) body topology inference, and (3) joint parameter estimation. The complete pipeline produces robot description files that are fully compatible with existing simulators. We validate our method across a variety of robots, using both synthetic and real-world scan data. Results indicate that our approach outperforms previous methods in registration and body topology estimation accuracy, offering a scalable solution for automated robot modeling.

Xu Yan, Jun Yin, Jie Wen

In incomplete multi-view multi-label learning scenarios, it is crucial to use the incomplete multi-view data to extract consistent and specific representations from different data sources and to fully exploit the missing label information. However, most previous approaches ignore the separation problem between view-shared and specific information. To address this problem, in this paper, we propose a method that can separate view-consistent features from view-specific features under the Variational Autoencoder (VAE) framework. Specifically, we first introduce cross-view reconstruction to capture view-consistent features and extract shared information from different views through unsupervised pre-training. Subsequently, we develop a disentangling module to learn specific features by minimizing the variational upper bound of mutual information between consistent and specific features. Finally, we utilize prior label relevance information derived from training data to guide the learning of the distribution of label semantic embeddings, aggregating relevant semantic embeddings and maintaining the label relevance topology in the semantic space. In extensive experiments, our model outperforms existing state-of-the-art algorithms on several real-world datasets, which fully validates its strong adaptability to missing views and labels.

Shehan Munasinghe, Hanan Gani, Wenqi Zhu, Jiale Cao, Eric Xing, Fahad Shahbaz Khan, Salman Khan

Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level grounding in videos. To address this, we introduce VideoGLaMM, a LMM designed for fine-grained pixel-level grounding in videos based on user-provided textual inputs. Our design seamlessly connects three key components: a Large Language Model, a dual vision encoder that emphasizes both spatial and temporal details, and a spatio-temporal decoder for accurate mask generation. This connection is facilitated via tunable V-L and L-V adapters that enable close Vision-Language (VL) alignment. The architecture is trained to synchronize both spatial and temporal elements of video content with textual instructions. To enable fine-grained grounding, we curate a multimodal dataset featuring detailed visually-grounded conversations using a semiautomatic annotation pipeline, resulting in a diverse set of 38k video-QA triplets along with 83k objects and 671k masks. We evaluate VideoGLaMM on three challenging tasks: Grounded Conversation Generation, Visual Grounding, and Referring Video Segmentation. Experimental results show that our model consistently outperforms existing approaches across all three tasks.

Xiangyuan Xue, Zeyu Lu, Di Huang, Zidong Wang, Wanli Ouyang, Lei Bai

Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast, this work attempts to study using LLM-based agents to design collaborative AI systems autonomously. To explore this problem, we first introduce ComfyBench to evaluate agents's ability to design collaborative AI systems in ComfyUI. ComfyBench is a comprehensive benchmark comprising 200 diverse tasks covering various instruction-following generation challenges, along with detailed annotations for 3,205 nodes and 20 workflows. Based on ComfyBench, we further develop ComfyAgent, a novel framework that empowers LLM-based agents to autonomously design collaborative AI systems by generating workflows. ComfyAgent is based on two core concepts. First, it represents workflows with code, which can be reversibly converted into workflows and executed as collaborative systems by the interpreter. Second, it constructs a multi-agent system that cooperates to learn from existing workflows and generate new workflows for a given task. While experimental results demonstrate that ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks. LLM-based agents still have a long way to go in autonomously designing collaborative AI systems. Progress with ComfyBench is paving the way for more intelligent and autonomous collaborative AI systems. Our code is available at: https://github.com/xxyQwQ/ComfyBench.

Yuanlin Wang, Yiyang Zhang, Ruiqin Xiong, Jing Zhao, Jian Zhang, Xiaopeng Fan, Tiejun Huang

Spike camera is a kind of neuromorphic camera that records dynamic scenes by firing a stream of binary spikes with extremely high temporal resolution. It demonstrates great potential for vision tasks in high-speed scenarios. One limitation in its current implementation is the relatively low spatial resolution. This paper develops a network called Spk2SRImgNet to super-resolve high resolution images from low resolution spike stream. However, fluctuations in spike stream hinder the performance of spike camera super resolution. To address this issue, we propose a motion aligned collaborative filtering (MACF) module, which is motivated by key ideas in classic image restoration schemes to mitigate fluctuations in spike data. MACF leverages the temporal similarity of spike stream to acquire similar features from neighboring moments via motion alignment. To separate disturbances from features, MACF filters these similar features jointly in transform domain to exploit representation sparsity, and generates refinement features that will be used to update initial fluctuated features. Specifically, MACF designs an inverse motion alignment operation to map these refinement features back to their original positions. The initial features are aggregated with the repositioned refinement features to enhance reliability. Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared with existing methods.

Awais Nizamani, Hamid Laga, Guanjin Wang, Farid Boussaid, Mohammed Bennamoun, Anuj Srivastava

We propose a novel framework for the statistical analysis of genus-zero 4D surfaces, i.e., 3D surfaces that deform and evolve overtime. This problem is particularly challenging due to the arbitrary parameterizations of these surfaces and their varying deformation speeds, necessitating effective spatiotemporal registration. Traditionally, 4D surfaces are discretized, in space and time, before computing their spatiotemporal registrations, geodesics and statistics. However, this approach may result in suboptimal solutions and, as we demonstrate in this paper, is not necessary. In contrast, we treat 4D surfaces as continuous functions in both space and time. We introduce Dynamic Spherical Neural Surfaces (D-SNS), an efficient smooth and continuous spatiotemporal representation for genus-0 4D surfaces. We then demonstrate how to perform core 4D shape analysis tasks such as spatiotemporal registration, geodesics computation, and mean 4D shape estimation, directly on these continuous representations without upfront discretization and meshing. By integrating neural representations with classical Riemannian geometry and statistical shape analysis techniques, we provide the building blocks for enabling full functional shape analysis. We demonstrate the efficiency of the framework on 4D human and face datasets.

Dušan Malić, Christian Fruhwirth-Reisinger, Samuel Schulter, Horst Possegger

While surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored. This is caused by the lack of large-scale annotated datasets on the one hand, and lack of methods that can robustly handle the sparse and often noisy LiDAR data in a reasonable time on the other hand. We address these limitations using a traffic simulation engine and present LiSu, the first large-scale, synthetic LiDAR point cloud dataset with ground truth surface normal annotations, eliminating the need for tedious manual labeling. Additionally, we propose a novel method that exploits the spatiotemporal characteristics of autonomous driving data to enhance surface normal estimation accuracy. By incorporating two regularization terms, we enforce spatial consistency among neighboring points and temporal smoothness across consecutive LiDAR frames. These regularizers are particularly effective in self-training settings, where they mitigate the impact of noisy pseudo-labels, enabling robust real-world deployment. We demonstrate the effectiveness of our method on LiSu, achieving state-of-the-art performance in LiDAR surface normal estimation. Moreover, we showcase its full potential in addressing the challenging task of synthetic-to-real domain adaptation, leading to improved neural surface reconstruction on real-world data.

Zongsheng Yue, Kang Liao, Chen Change Loy

This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise Prediction strategy to construct an intermediate state of the diffusion model, which serves as the starting sampling point. Central to our approach is a deep noise predictor to estimate the optimal noise maps for the forward diffusion process. Once trained, this noise predictor can be used to initialize the sampling process partially along the diffusion trajectory, generating the desirable high-resolution result. Compared to existing approaches, our method offers a flexible and efficient sampling mechanism that supports an arbitrary number of sampling steps, ranging from one to five. Even with a single sampling step, our method demonstrates superior or comparable performance to recent state-of-the-art approaches. The code and model will be made publicly available.

Yalong Xu, Lin Zhao, Chen Gong, Guangyu Li, Di Wang, Nannan Wang

Top-down approaches for human pose estimation (HPE) have reached a high level of sophistication, exemplified by models such as HRNet and ViTPose. Nonetheless, the low efficiency of top-down methods is a recognized issue that has not been sufficiently explored in current research. Our analysis suggests that the primary cause of inefficiency stems from the substantial diversity found in pose samples. On one hand, simple poses can be accurately estimated without requiring the computational resources of larger models. On the other hand, a more prominent issue arises from the abundance of bounding boxes, which remain excessive even after NMS. In this paper, we present a straightforward yet effective dynamic framework called DynPose, designed to match diverse pose samples with the most appropriate models, thereby ensuring optimal performance and high efficiency. Specifically, the framework contains a lightweight router and two pre-trained HPE models: one small and one large. The router is optimized to classify samples and dynamically determine the appropriate inference paths. Extensive experiments demonstrate the effectiveness of the framework. For example, using ResNet-50 and HRNet-W32 as the pre-trained models, our DynPose achieves an almost 50% increase in speed over HRNet-W32 while maintaining the same-level accuracy. More importantly, the framework can be generalized to other pre-trained models and datasets without re-training or fine-tuning. Code is available at https://github.com/Aritoria/DynPose.

Yihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Zhiheng Liu, Yujun Shen, Huamin Qu

The production of 2D animation follows an industry-standard workflow, encompassing four essential stages: character design, keyframe animation, in-betweening, and coloring. Our research focuses on reducing the labor costs in the above process by harnessing the potential of increasingly powerful generative AI. Using video diffusion models as the foundation, Anidoc emerges as a video line art colorization tool, which automatically converts sketch sequences into colored animations following the reference character specification. Our model exploits correspondence matching as an explicit guidance, yielding strong robustness to the variations (e.g., posture) between the reference character and each line art frame. In addition, our model could even automate the in-betweening process, such that users can easily create a temporally consistent animation by simply providing a character image as well as the start and end sketches. We will make the model public to facility the community.

Yulu Pan, Ce Zhang, Gedas Bertasius

We present BASKET, a large-scale basketball video dataset for fine-grained skill estimation. BASKET contains 4,477 hours of video capturing 32,232 basketball players from all over the world. Compared to prior skill estimation datasets, our dataset includes a massive number of skilled participants with unprecedented diversity in terms of gender, age, skill level, geographical location, etc. BASKET includes 20 fine-grained basketball skills, challenging modern video recognition models to capture the intricate nuances of player skill through in-depth video analysis. Given a long highlight video (8-10 minutes) of a particular player, the model needs to predict the skill level (e.g., excellent, good, average, fair, poor) for each of the 20 basketball skills. Our empirical analysis reveals that the current state-of-the-art video models struggle with this task, significantly lagging behind the human baseline. We believe that BASKET could be a useful resource for developing new video models with advanced long-range, fine-grained recognition capabilities. In addition, we hope that our dataset will be useful for domain-specific applications such as fair basketball scouting, personalized player development, and many others. Dataset and code are available at https://github.com/yulupan00/BASKET.

Unki Park, Seongmoon Jeong, Youngchan Jang, Gyeong-Moon Park, Jong Hwan Ko

The field of computer vision was initially inspired by the human visual system and has progressively expanded to include a broader range of machine vision applications. Consequently, image compressors should be designed to effectively accommodate not only human visual perception but also machine vision tasks, including closed-set scenarios that enable pre-training and open-set scenarios that involve previously unseen tasks at test time. Many recent studies effectively address both human visual perception and closed-set machine vision tasks simultaneously but struggle to handle open-set machine vision tasks. To address this issue, this paper proposes a fully instance-specific test time fine-tuning (TTFT) for adapting learned image compression (LIC) to both closed-set and open-set machine vision tasks effectively. With our method, a large-scale LIC model, originally trained for human perception, is adapted to the target task through TTFT using Singular Value Decomposition based Low Rank Adaptation (SVD-LoRA). During TTFT, the decoder adopts a modified learning scheme that focuses exclusively on training the singular values, which helps prevent excessive bitstream overhead. This enables fully instance-specific optimization for the target task, even for open-set tasks. Experimental results demonstrate that the proposed method effectively adapts the backbone compressor to diverse machine vision tasks, outperforming competing methods.

Biplab Das, Viswanath Gopalakrishnan

In this work, we introduce Camouflage Anything, a novel and robust approach to generate camouflaged datasets. To the best of our knowledge, we are the first to apply Controlled Out-painting and Representation Engineering for generating realistic camouflaged images with an objective to hide any segmented object coming from a generic or salient database. Our proposed method uses a novel control design to out-paint a given segmented object, with a camouflaged background. We also uncover the role of representation engineering in enhancing the quality of generated camouflage datasets. We address the limitations of existing metrics FID and KID in capturing the 'camouflage quality' ,by proposing a novel metric namely, CamOT. CamOT uses Optimal Transport between foreground & background Gaussian Mixture Models (GMM) of concerned camouflaged object to assign an image quality score. Furthermore, we conduct LoRA-based fine-tuning of the robust BiRefNet baseline with our generated camouflaged datasets, leading to notable improvements in camouflaged object segmentation accuracy. The experimental results showcase the efficacy and potential of Camouflage Anything, outperforming existing methods in camouflaged generation tasks.

Davide Caffagni, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Cross-modal retrieval is gaining increasing efficacy and interest from the research community, thanks to large-scale training, novel architectural and learning designs, and its application in LLMs and multimodal LLMs. In this paper, we move a step forward and design an approach that allows for multimodal queries - composed of both an image and a text - and can search within collections of multimodal documents, where images and text are interleaved. Our model, ReT, employs multi-level representations extracted from different layers of both visual and textual backbones, both at the query and document side. To allow for multi-level and cross-modal understanding and feature extraction, ReT employs a novel Transformer-based recurrent cell that integrates both textual and visual features at different layers, and leverages sigmoidal gates inspired by the classical design of LSTMs. Extensive experiments on M2KR and M-BEIR benchmarks show that ReT achieves state-of-the-art performance across diverse settings. Our source code and trained models are publicly available at: https://github.com/aimagelab/ReT.