An official website of the United States government
Traffic accident anticipation is a vital function of Automated Driving Systems (ADS) in providing a safety-guaranteed driving experience. An accident anticipation model aims to predict accidents promptly and accurately before they occur. Existing Artificial Intelligence (AI) models of accident anticipation lack a human-interpretable explanation of their decision making. Although these models perform well, they remain a black-box to the ADS users who find it to difficult to trust them. To this end, this paper presents a gated recurrent unit (GRU) network that learns spatio-temporal relational features for the early anticipation of traffic accidents from dashcam video data. A post-hoc attention mechanism named Grad-CAM (Gradient-weighted Class Activation Map) is integrated into the network to generate saliency maps as the visual explanation of the accident anticipation decision. An eye tracker captures human eye fixation points for generating human attention maps. The explainability of network-generated saliency maps is evaluated in comparison to human attention maps. Qualitative and quantitative results on a public crash data set confirm that the proposed explainable network can anticipate an accident on average 4.57 s before it occurs, with 94.02% average precision. Various post-hoc attention-based XAI methods are then evaluated and compared. This confirms that the Grad-CAM chosen by this study can generate high-quality, human-interpretable saliency maps (with 1.23 Normalized Scanpath Saliency) for explaining the crash anticipation decision. Importantly, results confirm that the proposed AI model, with a human-inspired design, can outperform humans in accident anticipation.
more »
« less
This content will become publicly available on December 7, 2026
Learning to Look: Cognitive Attention Alignment with Vision-Language Models
Convolutional Neural Networks (CNNs) frequently “cheat” by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of attention in robust human perception, recent methods have sought to guide model attention using concept-based supervision and explanation regularization. However, these techniques depend on labor-intensive, expert-provided annotations, limiting their scalability. We propose a scalable framework that leverages vision-language models to automatically generate semantic attention maps using natural language prompts. By introducing an auxiliary loss that aligns CNN attention with these language-guided maps, our approach promotes more reliable and cognitively plausible decision-making without manual annotation. Experiments on challenging datasets, ColoredMNIST and DecoyMNIST, show that our method achieves stateof- the-art performance on ColorMNIST and remains competitive with annotationheavy baselines on DecoyMNIST, demonstrating improved generalization, reduced shortcut reliance, and model attention that better reflects human intuition. Our code is available at https://github.com/ryanlyang/LearningToLook/.
more »
« less
- Award ID(s):
- 2447631
- PAR ID:
- 10646783
- Publisher / Repository:
- 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: First Workshop on CogInterp: Interpreting Cognition in Deep Learning Models.
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Knowledge distillation aims at reducing model size without compromising much performance. Recent work has applied it to large vision-language (VL) Transformers, and has shown that attention maps in the multi-head attention modules of vision-language Transformers contain extensive intra-modal and cross-modal co-reference relations to be distilled. The standard approach is to apply a one-to-one attention map distillation loss, i.e. the Teacher’s first attention head instructs the Student’s first head, the second teaches the second, and so forth, but this only works when the numbers of attention heads in the Teacher and Student are the same. To remove this constraint, we propose a new Attention Map Alignment Distillation (AMAD) method for Transformers with multi-head attention, which works for a Teacher and a Student with different numbers of attention heads. Specifically, we soft-align different heads in Teacher and Student attention maps using a cosine similarity weighting. The Teacher head contributes more to the Student heads for which it has a higher similarity weight. Each Teacher head contributes to all the Student heads by minimizing the divergence between the attention activation distributions for the soft-aligned heads. No head is left behind. This distillation approach operates like cross-attention. We experiment on distilling VL-T5 and BLIP, and apply AMAD loss on their T5, BERT, and ViT sub-modules. We show, under vision-language setting, that AMAD outperforms conventional distillation methods on VQA-2.0, COCO captioning, and Multi30K translation datasets. We further show that even without VL pre-training, the distilled VL-T5 models outperform corresponding VL pre-trained VL-T5 models that are further fine-tuned by ground-truth signals, and that fine-tuning distillation can also compensate to some degree for the absence of VL pre-training for BLIP models.more » « less
-
Faust, Aleksandra; Hsu, David; Neumann, Gerhard (Ed.)Enabling human operators to interact with robotic agents using natural language would allow non-experts to intuitively instruct these agents. Towards this goal, we propose a novel Transformer-based model which enables a user to guide a robot arm through a 3D multi-step manipulation task with natural language commands. Our system maps images and commands to masks over grasp or place locations, grounding the language directly in perceptual space. In a suite of block rearrangement tasks, we show that these masks can be combined with an existing manipulation framework without re-training, greatly improving learning efficiency. Our masking model is several orders of magnitude more sample efficient than typical Transformer models, operating with hundreds, not millions, of examples. Our modular design allows us to leverage supervised and reinforcement learning, providing an easy interface for experimentation with different architectures. Our model completes block manipulation tasks with synthetic commands more often than a UNet-based baseline, and learns to localize actions correctly while creating a mapping of symbols to perceptual input that supports compositional reasoning. We provide a valuable resource for 3D manipulation instruction following research by porting an existing 3D block dataset with crowdsourced language to a simulated environment. Our method’s absolute improvement in identifying the correct block on the ported dataset demonstrates its ability to handle syntactic and lexical variation.more » « less
-
Drawing language maps is not normally considered an important part of linguists’ work. Nonetheless, language maps influence their users’ perceptions and understandings of the characteristics of the languages that they represent. Therefore, given their communicative power, wide accessibility, and generalized use for educational purposes, attention must be paid as to what messages language maps convey about the languages that they visualize since different cartographic styles can be suited to representing some language ecologies better than others. However, decisions at this level are not normally made explicit by cartographers, and the ways in which certain ideologies surface in language maps can escape the attention of both linguists and cartographers alike. This article clarifies why these issues are especially relevant in a domain such as that of the study of Bantoid languages and proposes some novel cartographic models that have been used for representing the languages of Lower Fungom in western Cameroon. These include some cartographic strategies for the representation of the language ideologies of speaker communities and of individual multilingualism. The latter is both a key and under-researched feature in Bantoid sociolinguistics and the article suggests how scholars who are not sociolinguists may nevertheless contribute to its exploration.more » « less
-
Large Language Models (LLMs) have recently been widely used for code generation. Due to the complexity and opacity of LLMs, little is known about how these models generate code. We made the first attempt to bridge this knowledge gap by investigating whether LLMs attend to the same parts of a task description as human programmers during code generation. An analysis of six LLMs, including GPT-4, on two popular code generation benchmarks revealed a consistent misalignment between LLMs' and programmers' attention. We manually analyzed 211 incorrect code snippets and found five attention patterns that can be used to explain many code generation errors. Finally, a user study showed that model attention computed by a perturbation-based method is often favored by human programmers. Our findings highlight the need for human-aligned LLMs for better interpretability and programmer trust.more » « less
