T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory

Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from unreliable predictions under distribution shifts during test time. Accordingly, several online learning methods have been proposed using regression loss from the ground truth of observed data leveraging the auto-labeling nature of trajectory prediction task. We mainly tackle the following two issues. First, previous works underfit and overfit as they only optimize the last layer of the motion decoder. To this end, we employ the masked autoencoder (MAE) for representation learning to encourage complex interaction modeling in shifted test distribution for updating deeper layers. Second, utilizing the sequential nature of driving data, we propose an actor-specific token memory that enables the test-time learning of actor-wise motion characteristics. Our proposed method has been validated across various challenging cross-dataset distribution shift scenarios including nuScenes, Lyft, Waymo, and Interaction. Our method surpasses the performance of existing state-of-the-art online learning methods in terms of both prediction accuracy and computational efficiency. The code is available at https://github.com/daeheepark/T4P.

Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation

Existing studies in weakly supervised semantic segmentation (WSSS) have utilized class activation maps (CAMs) to localize the class objects. However, since a classification loss is insufficient for providing precise object regions, CAMs tend to be biased towards discriminative patterns (i.e., sparseness) and do not provide precise object boundary information (i.e., impreciseness). To resolve these limitations, we propose a novel framework (composed of MainNet and SupportNet.) that derives pixel-level self-supervision from given image-level supervision. In our framework, with the help of the proposed Regional Contrastive Module (RCM) and Multi-scale Attentive Module (MAM), MainNet is trained by self-supervision from the SupportNet. The RCM extracts two forms of self-supervision from SupportNet: (1) class region masks generated from the CAMs and (2) class-wise prototypes obtained from the features according to the class region masks. Then, every pixel-wise feature of the MainNet is trained by the prototype in a contrastive manner, sharpening the resulting CAMs. The MAM utilizes CAMs inferred at multiple scales from the SupportNet as self-supervision to guide the MainNet. Based on the dissimilarity between the multi-scale CAMs from MainNet and SupportNet, CAMs from the MainNet are trained to expand to the less-discriminative regions. The proposed method shows state-of-the-art WSSS performance both on the train and validation sets on the PASCAL VOC 2012 dataset. For reproducibility, code will be available publicly soon.

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation

Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A hurdle of training event-based models is the lack of large qualitative labeled data. Prior works learning end-tasks mostly rely on labeled or pseudo-labeled datasets obtained from the active pixel sensor (APS) frames; however, such datasets' quality is far from rivaling those based on the canonical images. In this paper, we propose a novel approach, called \textbf{EvDistill}, to learn a student network on the unlabeled and unpaired event data (target modality) via knowledge distillation (KD) from a teacher network trained with large-scale, labeled image data (source modality). To enable KD across the unpaired modalities, we first propose a bidirectional modality reconstruction (BMR) module to bridge both modalities and simultaneously exploit them to distill knowledge via the crafted pairs, causing no extra computation in the inference. The BMR is improved by the end-tasks and KD losses in an end-to-end manner. Second, we leverage the structural similarities of both modalities and adapt the knowledge by matching their distributions. Moreover, as most prior feature KD methods are uni-modality and less applicable to our problem, we propose to leverage an affinity graph KD loss to boost the distillation. Our extensive experiments on semantic segmentation and object recognition demonstrate that EvDistill achieves significantly better results than the prior works and KD with only events and APS frames.