We thank the reviewers for their detailed and thoughtful comments. These are not new and have been presented thoroughly in the submitted paper. Our intention was not to challenge the momentum mechanism. Combining SwA V with a momentum encoder and/or a large memory bank are indeed interesting follow-ups. In Tab.5, we make a best effort fair comparison (same data augmentation, num.

Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity enhancement (NHDE) to produce more Pareto solutions from two perspectives. On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph. On the other hand, to excavate more solutions in the neighborhood of each subproblem, we present a multiple Pareto optima strategy to sample and preserve desirable solutions. Experimental results on classic MOCO problems show that our NHDE is able to generate a Pareto front with higher diversity, thereby achieving superior overall performance. Moreover, our NHDE is generic and can be applied to different neural methods for MOCO.

We thank the reviewers for valuable feedback. Before addressing individual comments, we clarify common concerns. Moreover, "image-level" vs "pixel-level" training has no bearing on the validity of evaluating with Any method that uses a CNN learns more than just "image-level" representations; for Our task is to learn pixel-wise semantic-aware embeddings from scratch. We will update the final version to reflect the full 200 training epochs. We first sample regions, then a fixed number of pixels within chosen regions.

Table 1 reports the results of a controlled experiment evaluating different components in our framework for auxiliary label generation. Positive correspondences are generated by matching pixels across different augmentations of the same image. With respect to the clustering algorithm, K-means performs better than DBSCAN (#4 vs. #5), which is We show qualitative results, comparing different feature extractors in Figure 1. DBSCAN is limited by the memory and computational complexity. Corresponding qualitative results are shown in Figure 3. Tables 3-5 show We observe the best performance when 5% outliers are removed.