论文检索

Deep Learning · Other Representation Learning

Andreas Abildtrup Hansen, Anna Calissano, Aasa Feragen

Latent representations are extensively used for tasks like visualization, interpolation, or feature extraction in deep learning models. This paper demonstrates the importance of considering the inductive bias imposed by an equivariant model when using latent representations as neglecting these biases can lead to decreased performance in downstream tasks. We propose principles for choosing invariant projections of latent representations and show their effectiveness in two examples: A permutation equivariant variational auto-encoder for molecular graph generation, where an invariant projection can be designed to maintain information without loss, and for a rotation-equivariant representation in image classification, where random invariant projections proves to retain a high degree of information. In both cases, the analysis of invariant latent representations proves superior to their equivariant counterparts. Finally, we illustrate that the phenomena documented here for equivariant neural networks have counterparts in standard neural networks where invariance is encouraged via augmentation.

Applications · Robotics

Hyunki Seong, Hyunchul Shim

We introduce MoNet, a novel functionally modular network for self-supervised and interpretable end-to-end learning. By leveraging its functional modularity with a latent-guided contrastive loss function, MoNet efficiently learns task-specific decision-making processes in latent space without requiring task-level supervision. Moreover, our method incorporates an online, post-hoc explainability approach that enhances the interpretability of end-to-end inferences without compromising sensorimotor control performance. In real-world indoor environments, MoNet demonstrates effective visual autonomous navigation, outperforming baseline models by 7% to 28% in task specificity analysis. We further explore the interpretability of our network through post-hoc analysis of perceptual saliency maps and latent decision vectors. This provides valuable insights into the incorporation of explainable artificial intelligence into robotic learning, encompassing both perceptual and behavioral perspectives. Supplementary materials are available at https://sites.google.com/view/monet-lgc.

Deep Learning · Large Language Models

Zhaorun Chen, Zhuokai Zhao, HONGYIN LUO, Huaxiu Yao, Bo Li, Jiawei Zhou

While large vision-language models (LVLMs) have demonstrated impressive capabilities in interpreting multi-modal contexts, they invariably suffer from object hallucinations (OH). We introduce HALC, a novel decoding algorithm designed to mitigate OH in LVLMs. HALC leverages distinct fine-grained optimal visual information in vision-language tasks and operates on both local and global contexts simultaneously. Specifically, HALC integrates a robust auto-focal grounding mechanism (locally) to correct hallucinated tokens on the fly, and a specialized beam search algorithm (globally) to significantly reduce OH while preserving text generation quality. Additionally, HALC can be integrated into any LVLMs as a plug-and-play module without extra training. Extensive experimental studies demonstrate HALC’s effectiveness in reducing OH, outperforming state-of-the-arts across four benchmarks. Code is released at https://github.com/BillChan226/HALC.

Social Aspects · Accountability, Transparency and Interpretability

Arshia Soltani Moakhar, Eugenia Iofinova, Elias Frantar, Dan Alistarh

It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the network's general behavior. In this paper, we demonstrate, for the first time, that sparsity can instead be incorporated into the interpretation process itself, as a sample-specific preprocessing step. Unlike previous work, this approach, which we call SPADE, does not place constraints on the trained model and does not affect its behavior during inference on the sample. Given a trained model and a target sample, SPADE uses sample-targeted pruning to provide a "trace" of the network's execution on the sample, reducing the network to the most important connections prior to computing an interpretation. We demonstrate that preprocessing with SPADE significantly increases the accuracy of image saliency maps across several interpretability methods. Additionally, SPADE improves the usefulness of neuron visualizations, aiding humans in reasoning about network behavior. Our code is available at https://github.com/IST-DASLab/SPADE.

Social Aspects · Accountability, Transparency and Interpretability

Aaron Li, Robin Netzorg, Zhihan Cheng, Zhuoqin Zhang, Bin Yu

In recent years, work has gone into developing deep interpretable methods for image classification that clearly attributes a model's output to specific features of the data. One such of these methods is the Prototypical Part Network (ProtoPNet), which attempts to classify images based on meaningful parts of the input. While this architecture is able to produce visually interpretable classifications, it often learns to classify based on parts of the image that are not semantically meaningful. To address this problem, we propose the Reward Reweighing, Reselecting, and Retraining (R3) post-processing framework, which performs three additional corrective updates to a pretrained ProtoPNet in an offline and efficient manner. The first two steps involve learning a reward model based on collected human feedback and then aligning the prototypes with human preferences. The final step is retraining, which realigns the base features and the classifier layer of the original model with the updated prototypes. We find that our R3 framework consistently improves both the interpretability and the predictive accuracy of ProtoPNet and its variants.

Reinforcement Learning · Deep RL

Jessy Lin, Yuqing Du, Olivia Watkins, Danijar Hafner, Pieter Abbeel, Dan Klein, Anca Dragan

To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents that leverage diverse language---language like "this button turns on the TV" or "I put the bowls away"---that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that *agents should interpret such diverse language as a signal that helps them predict the future*: what they will observe, how the world will behave, and which situations will be rewarded. This perspective unifies language understanding with future prediction as a powerful self-supervised learning objective. We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations, and learns to act from imagined model rollouts. While current methods that learn language-conditioned policies degrade in performance with more diverse types of language, we show that Dynalang learns to leverage environment descriptions, game rules, and instructions to excel on tasks ranging from game-playing to navigating photorealistic home scans. Finally, we show that our method enables additional capabilities due to learning a generative model: Dynalang can be pretrained on text-only data, enabling learning from offline datasets, and generate language grounded in an environment.

Applications · Computer Vision

Chenyang ZHAO, Kun Wang, Xingyu Zeng, Rui Zhao, Antoni Chan

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a Gradient-based visual Explanation method for CLIP (Grad-ECLIP), which interprets the matching result of CLIP for specific input image-text pair. By decomposing the architecture of the encoder and discovering the relationship between the matching similarity and intermediate spatial features, Grad-ECLIP produces effective heat maps that show the influence of image regions or words on the CLIP results. Different from the previous Transformer interpretation methods that focus on the utilization of self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights on token features. Qualitative and quantitative evaluations verify the superiority of Grad-ECLIP compared with the state-of-the-art methods. A series of analysis are conducted based on our visual explanation results, from which we explore the working mechanism of image-text matching, and the strengths and limitations in attribution identification of CLIP. Codes are available here: https://github.com/Cyang-Zhao/Grad-Eclip.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Jun-Peng Jiang, Han-Jia Ye, Leye Wang, Yang Yang, Yuan Jiang, De-Chuan Zhan

Transferring knowledge across diverse data modalities is receiving increasing attention in machine learning. This paper tackles the task of leveraging expert-derived, yet expensive, tabular data to enhance image-based predictions when tabular data is unavailable during inference. The primary challenges stem from the inherent complexity of accurately mapping diverse tabular data to visual contexts, coupled with the necessity to devise distinct strategies for numerical and categorical tabular attributes. We propose CHannel tAbulaR alignment with optiMal tranSport (Charms), which establishes an alignment between image channels and tabular attributes, enabling selective knowledge transfer that is pertinent to visual features. Specifically, Charms measures similarity distributions across modalities to effectively differentiate and transfer relevant tabular features, with a focus on morphological characteristics, enhancing the capabilities of visual classifiers. By maximizing the mutual information between image channels and tabular features, knowledge from both numerical and categorical tabular attributes are extracted. Experimental results demonstrate that Charms not only enhances the performance of image classifiers but also improves their interpretability by effectively utilizing tabular knowledge.

Social Aspects · Trustworthy Machine Learning

Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with visual observations, but previous methods cannot refine the structured states with rewards due to a lack of efficiency. Accessibility also remains an issue, as extensive domain knowledge is required to interpret symbolic policies. In this paper, we present a neuro-symbolic framework for jointly learning structured states and symbolic policies, whose key idea is to distill the vision foundation model into an efficient perception module and refine it during policy learning. Moreover, we design a pipeline to prompt GPT-4 to generate textual explanations for the learned policies and decisions, significantly reducing users' cognitive load to understand the symbolic policies. We verify the efficacy of our approach on nine Atari tasks and present GPT-generated explanations for policies and decisions.

Deep Learning · Large Language Models

Rohan Wadhawan, Hritik Bansal, Kai-Wei Chang, Nanyun Peng

Many real-world tasks require an agent to reason jointly over text and visual objects, (e.g., navigating in public spaces), which we refer to as context-sensitive text-rich visual reasoning. Specifically, these tasks require an understanding of the context in which the text interacts with visual elements within an image. However, there is a lack of existing datasets to benchmark the state-of-the-art multimodal models' capability on context-sensitive text-rich visual reasoning. In this paper, we introduce ConTextual, a novel dataset featuring human-crafted instructions that require context-sensitive reasoning for text-rich images. We conduct experiments to assess the performance of 14 foundation models (GPT-4V, Gemini-Pro-Vision, LLaVA-Next) and establish a human performance baseline. Further, we perform human evaluations of the model responses and observe a significant performance gap of 30.8% between GPT-4V (the current best-performing Large Multimodal Model) and human performance. Our fine-grained analysis reveals that GPT-4V encounters difficulties interpreting time-related data and infographics. However, it demonstrates proficiency in comprehending abstract visual contexts such as memes and quotes. Finally, our qualitative analysis uncovers various factors contributing to poor performance including lack of precise visual perception and hallucinations. Our dataset, code, and leaderboard can be found on the project page https://con-textual.github.io/.

Deep Learning · Generative Models and Autoencoders

Weili Nie, Sifei Liu, Morteza Mardani, Chao Liu, Benjamin Eckart, Arash Vahdat

Existing text-to-image models struggle to follow complex text prompts, raising the need for extra grounding inputs for better controllability. In this work, we propose to decompose a scene into visual primitives - denoted as dense blob representations - that contain fine-grained details of the scene while being modular, human-interpretable, and easy-to-construct. Based on blob representations, we develop a blob-grounded text-to-image diffusion model, termed BlobGEN, for compositional generation. Particularly, we introduce a new masked cross-attention module to disentangle the fusion between blob representations and visual features. To leverage the compositionality of large language models (LLMs), we introduce a new in-context learning approach to generate blob representations from text prompts. Our extensive experiments show that BlobGEN achieves superior zero-shot generation quality and better layout-guided controllability on MS-COCO. When augmented by LLMs, our method exhibits superior numerical and spatial correctness on compositional image generation benchmarks.

Yixiong Zou, Shanghang Zhang, haichen zhou, Yuhua Li, Ruixuan Li

Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans can easily recognize novel classes with a few samples. Cognitive science demonstrates that an important component of such human capability is compositional learning. This involves identifying visual primitives from learned knowledge and then composing new concepts using these transferred primitives, making incremental learning both effective and interpretable. To imitate human compositional learning, we propose a cognitive-inspired method for the FSCIL task. We define and build a compositional model based on set similarities, and then equip it with a primitive composition module and a primitive reuse module. In the primitive composition module, we propose to utilize the Centered Kernel Alignment (CKA) similarity to approximate the similarity between primitive sets, allowing the training and evaluation based on primitive compositions. In the primitive reuse module, we enhance primitive reusability by classifying inputs based on primitives replaced with the closest primitives from other classes. Experiments on three datasets validate our method, showing it outperforms current state-of-the-art methods with improved interpretability. Our code is available at https://github.com/Zoilsen/Comp-FSCIL.

Applications · Computer Vision

Haoyu Zhang, Meng Liu, Zixin Liu, Xuemeng Song, Yaowei Wang, Liqiang Nie

The challenge of interpreting the world from a human perspective in Artificial Intelligence (AI) is particularly evident in egocentric video question answering, which grapples with issues like small object recognition, noise suppression, and spatial-temporal reasoning. To address these challenges, we introduce the Multi-Factor Adaptive vision Selection (MFAS) framework. MFAS integrates a patch partition and merging module for enhanced small object recognition, a prior-guided patch selection module for noise suppression and focused analysis, and a hierarchical aggregation network to aggregate visual semantics guided by questions. Extensive experiments on several public egocentric datasets have validated the effectiveness and generalization of our framework. Code and data are available in https://github.com/Hyu-Zhang/EgoVideoQA.

Applications · Computer Vision

Zhongze Wu, Hongyan Xu, Yitian Long, Shan You, Xiu Su, Jun Long, Yueyi Luo, Chang Xu

Medical Visual Question Answering (Med-VQA) interprets complex medical imagery using user instructions for precise diagnostics, yet faces challenges due to diverse, inadequately annotated images. In this paper, we introduce the Universal Instruction-Vision Navigator (Uni-Med) framework for extracting instruction-to-answer relationships, facilitating the understanding of visual evidence behind responses. Specifically, we design the Instruct-to-Answer Clues Interpreter (IAI) to generate visual explanations based on the answers and mark the core part of instructions with "real intent" labels. The IAI-Med VQA dataset, produced using IAI, is now publicly available to advance Med-VQA research. Additionally, our Token-Level Cut-Mix module dynamically aligns visual explanations with image patches, ensuring answers are traceable and learnable. We also implement intention-guided attention to minimize non-core instruction interference, sharpening focus on 'real intent'. Extensive experiments on SLAKE datasets show Uni-Med’s superior accuracies (87.52% closed, 86.12% overall), outperforming MedVInT-PMC-VQA by 1.22% and 0.92%. Code and dataset are available at: https://github.com/zhongzee/Uni-Med-master.

Social Aspects · Accountability, Transparency and Interpretability

Eslam Zaher, Maciej Trzaskowski, Quan Nguyen, Fred Roosta

In this paper, we dive into the reliability concerns of Integrated Gradients (IG), a prevalent feature attribution method for black-box deep learning models. We particularly address two predominant challenges associated with IG: the generation of noisy feature visualizations for vision models and the vulnerability to adversarial attributional attacks. Our approach involves an adaptation of path-based feature attribution, aligning the path of attribution more closely to the intrinsic geometry of the data manifold. Our experiments utilise deep generative models applied to several real-world image datasets. They demonstrate that IG along the geodesics conforms to the curved geometry of the Riemannian data manifold, generating more perceptually intuitive explanations and, subsequently, substantially increasing robustness to targeted attributional attacks.

Yi Wang, Zhiren Wang

We examine both the manifold hypothesis (Bengio et al., 2013) and the union of manifold hypothesis (Brown et al., 2023), and argue that, in contrast to these hypotheses, the local intrinsic dimension varies from point to point even in the same connected component. We propose an alternative CW complex hypothesis that image data is distributed in ``manifolds with skeletons". We support the hypothesis through visualization of distributions of image data of random geometric objects, as well as by introducing and testing a criterion on natural image datasets. One motivation of our work is to explain why diffusion models have difficulty generating accurate higher dimensional details such as human hands. Under the CW complex hypothesis and with both theoretical and empirical evidences, we provide an interpretation that the mixture of higher and lower dimensional components in data obstructs diffusion models from efficient learning.

Applications · Robotics

Longxin Kou, Fei Ni, Yan Zheng, Jinyi Liu, Yifu Yuan, Zibin Dong, Jianye Hao

Robotic manipulation tasks often span over long horizons and encapsulate multiple subtasks with different skills. Learning policies directly from long-horizon demonstrations is challenging without intermediate keyframes guidance and corresponding skill annotations. Existing approaches for keyframe identification often struggle to offer reliable decomposition for low accuracy and fail to provide semantic relevance between keyframes and skills. For this, we propose a unified **K**eyframe **I**dentifier and **S**kill **A**notator (**KISA**) that utilizes pretrained visual-language representations for precise and interpretable decomposition of unlabeled demonstrations. Specifically, we develop a simple yet effective temporal enhancement module that enriches frame-level representations with expanded receptive fields to capture semantic dynamics at the video level. We further propose coarse contrastive learning and fine-grained monotonic encouragement to enhance the alignment between visual representations from keyframes and language representations from skills. The experimental results across three benchmarks demonstrate that KISA outperforms competitive baselines in terms of accuracy and interpretability of keyframe identification. Moreover, KISA exhibits robust generalization capabilities and the flexibility to incorporate various pretrained representations.

Applications · Computer Vision

Deyi Ji, Feng Zhao, Lanyun Zhu, Wenwei Jin, Hongtao Lu, Jieping Ye

In this paper, we address the challenge of Perspective-Invariant Learning in machine learning and computer vision, which involves enabling a network to understand images from varying perspectives to achieve consistent semantic interpretation. While standard approaches rely on the labor-intensive collection of multi-view images or limited data augmentation techniques, we propose a novel framework, Discrete Latent Perspective Learning (DLPL), for latent multi-perspective fusion learning using conventional single-view images. DLPL comprises three main modules: Perspective Discrete Decomposition (PDD), Perspective Homography Transformation (PHT), and Perspective Invariant Attention (PIA), which work together to discretize visual features, transform perspectives, and fuse multi-perspective semantic information, respectively. DLPL is a universal perspective learning framework applicable to a variety of scenarios and vision tasks. Extensive experiments demonstrate that DLPL significantly enhances the network's capacity to depict images across diverse scenarios (daily photos, UAV, auto-driving) and tasks (detection, segmentation).

Social Aspects · Accountability, Transparency and Interpretability

Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau, Wieland Brendel, Been Kim

How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization. Today, visualization methods form the foundation of our knowledge about the internal workings of neural networks, as a type of mechanistic interpretability. Here we ask: How reliable are feature visualizations? We start our investigation by developing network circuits that trick feature visualizations into showing arbitrary patterns that are completely disconnected from normal network behavior on natural input. We then provide evidence for a similar phenomenon occurring in standard, unmanipulated networks: feature visualizations are processed very differently from standard input, casting doubt on their ability to "explain" how neural networks process natural images. This can be used as a sanity check for feature visualizations. We underpin our empirical findings by theory proving that the set of functions that can be reliably understood by feature visualization is extremely small and does not include general black-box neural networks. Therefore, a promising way forward could be the development of networks that enforce certain structures in order to ensure more reliable feature visualizations.

Social Aspects · Accountability, Transparency and Interpretability

Dan Friedman, Andrew Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun

A common method to study deep learning systems is to use simplified model representations—for example, using singular value decomposition to visualize the model’s hidden states in a lower dimensional space. This approach assumes that the results of these simplifications are faithful to the original model. Here, we illustrate an important caveat to this assumption: even if the simplified representations can accurately approximate the full model on the training set, they may fail to accurately capture the model’s behavior out of distribution. We illustrate this by training Transformer models on controlled datasets with systematic generalization splits, including the Dyck balanced-parenthesis languages and a code completion task. We simplify these models using tools like dimensionality reduction and clustering, and then explicitly test how these simplified proxies match the behavior of the original model. We find consistent generalization gaps: cases in which the simplified proxies are more faithful to the original model on the in-distribution evaluations and less faithful on various tests of systematic generalization. This includes cases where the original model generalizes systematically but the simplified proxies fail, and cases where the simplified proxies generalize better. Together, our results raise questions about the extent to which mechanistic interpretations derived using tools like SVD can reliably predict what a model will do in novel situations.