Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval

TL;DR

Efficient-SAM2 enhances SAM2's video object segmentation by focusing computation on salient object regions using object-aware routing and memory retrieval, achieving significant speedup with minimal accuracy loss.

Contribution

The paper introduces Efficient-SAM2, a post-training acceleration method that adaptively reduces redundant computation by leveraging object saliency and temporal consistency.

Findings

Achieves 1.68x speedup on SAM2.1-L model.

Only 1.0% accuracy drop on SA-V test set.

Reduces unnecessary background computation effectively.

Abstract

Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video processing. Although there have been efforts to improve the efficiency of SAM2, most of them focus on retraining a lightweight backbone, with little exploration into post-training acceleration. In this paper, we observe that SAM2 exhibits sparse perception pattern as biological vision, which provides opportunities for eliminating redundant computation and acceleration: i) In mask decoder, the attention primarily focuses on the foreground objects, whereas the image encoder in the earlier stage exhibits a broad attention span, which results in unnecessary computation to background regions. ii) In memory bank, only a small subset of tokens in each frame contribute significantly to memory attention, and the salient regions exhibit temporal consistency, making full-token computation redundant. With these insights, we propose Efficient-SAM2, which promotes SAM2 to adaptively focus on object regions while eliminating task-irrelevant computations, thereby significantly improving inference efficiency. Specifically, for image encoder, we propose object-aware Sparse Window Routing (SWR), a window-level computation allocation mechanism that leverages the consistency and saliency cues from the previous-frame decoder to route background regions into a lightweight shortcut branch. Moreover, for memory attention, we propose object-aware Sparse Memory Retrieval (SMR), which allows only the salient memory tokens in each frame to participate in computation, with the saliency pattern reused from their first recollection. With negligible additional parameters and minimal training overhead, Efficient-SAM2 delivers 1.68x speedup on SAM2.1-L model with only 1.0% accuracy drop on SA-V test set.