We study image segmentation in the biological domain, particularly trait and part segmentation from specimen images (e.g., butterfly wing stripes or beetle body parts). This is a crucial, fine-grained task that aids in understanding the biology of organisms. The conventional approach involves hand-labeling masks, often for hundreds of images per species, and training a segmentation model to generalize these labels to other images, which can be exceedingly laborious. We present a label-efficient method named Static Segmentation by Tracking (SST). SST is built upon the insight: while specimens of the same species have inherent variations, the traits and parts we aim to segment show up consistently. This motivates us to concatenate specimen images into a ``pseudo-video'' and reframe trait and part segmentation as a tracking problem. Concretely, SST generates masks for unlabeled images by propagating annotated or predicted masks from the ``pseudo-preceding'' images. Powered by Segment Anything Model 2 (SAM~2) initially developed for video segmentation, we show that SST can achieve high-quality trait and part segmentation with merely one labeled image per species -- a breakthrough for analyzing specimen images. We further develop a cycle-consistent loss to fine-tune the model, again using one labeled image. Additionally, we highlight the broader potential of SST, including one-shot instance segmentation on images taken in the wild and trait-based image retrieval.

Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts of labeled data to train. In this work, we introduce an innovative pre-training approach, Grounded Point Colorization (GPC), to bridge the gap between data and labels by teaching the model to colorize LiDAR point clouds, equipping it with valuable semantic cues. To tackle challenges arising from color variations and selection bias, we incorporate color as "context" by providing ground-truth colors as hints during colorization. Even with limited labeled data, GPC significantly improves finetuning performance; notably, on just 20% of the KITTI dataset, GPC outperforms training from scratch with the entire dataset. In sum, we introduce a fresh perspective on pre-training for 3D object detection, aligning the objective with the model's intended role and ultimately advancing the accuracy and efficiency of 3D object detection for autonomous vehicles. Detecting objects such as vehicles and pedestrians in 3D is crucial for self-driving cars to operate safely. Mainstream 3D object detectors (Shi et al., 2019; 2020b; Zhu et al., 2020; He et al., 2020a) take LiDAR point clouds as input, which provide precise 3D signals of the surrounding environment. However, training a detector needs a lot of labeled data. The expensive process of curating annotated data has motivated the community to investigate model pre-training using unlabeled data that can be collected easily. Most of the existing pre-training methods are built upon contrastive learning (Yin et al., 2022; Xie et al., 2020; Zhang et al., 2021; Huang et al., 2021; Liang et al., 2021), inspired by its success in 2D recognition (Chen et al., 2020a; He et al., 2020b). The key novelties, however, are often limited to how the positive and negative data pairs are constructed. This paper attempts to go beyond contrastive learning by providing a new perspective on pre-training 3D object detectors. We rethink pre-training's role in how it could facilitate the downstream fine-tuning with labeled data.

Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by re-sampling or re-weighting. In this paper, we investigate a largely overlooked approach -- post-processing calibration of confidence scores. We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size. We show that separately handling the background class and normalizing the scores over classes for each proposal are keys to achieving superior performance. On the LVIS dataset, NorCal can effectively improve nearly all the baseline models not only on rare classes but also on common and frequent classes. Finally, we conduct extensive analysis and ablation studies to offer insights into various modeling choices and mechanisms of our approach.