We lifted 10 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| chen960/ca-jaccard | canonical | 5 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| cm | Ran | chen960/ca-jaccard/caj/models/cm.py code served (permissive licence) · get_code("10ba7332fd4a54eb") |
| conv3x3 | Ran | chen960/ca-jaccard/caj/models/resnet_ibn_a.py code served (permissive licence) · get_code("fac5364e2f53c6db") |
| process_dir | Ran | chen960/ca-jaccard/caj/datasets/dukemtmcreid.py code served (permissive licence) · get_code("7e822f939fbe184f") |
| resnet101_ibn_a | Ran | chen960/ca-jaccard/caj/models/resnet_ibn_a.py code served (permissive licence) · get_code("c7f5d45660e6ec13") |
| resnet50_ibn_a | Ran | chen960/ca-jaccard/caj/models/resnet_ibn_a.py code served (permissive licence) · get_code("93cbdbc352d644d9") |
| build_pooling_layer | Not yet run | chen960/ca-jaccard/caj/models/pooling.py code served (permissive licence) · get_code("5c5d2f6f3c01ba6c") |
| extract_cnn_feature | Not yet run | chen960/ca-jaccard/caj/evaluators.py code served (permissive licence) · get_code("fbb5efeed7ebfd09") |
| extract_features | Not yet run | chen960/ca-jaccard/caj/evaluators.py code served (permissive licence) · get_code("962810c012a60817") |
| label_generator_kmeans | Not yet run | chen960/ca-jaccard/caj/models/kmeans.py code served (permissive licence) · get_code("4560dc753fea5981") |
| pairwise_distance | Not yet run | chen960/ca-jaccard/caj/evaluators.py code served (permissive licence) · get_code("b6d5887f94b1db25") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Person re-identification (re-ID) is a challenging task that aims to learn discriminative features for person retrieval. In person re-ID, Jaccard distance is a widely used distance metric, especially in re-ranking and clustering scenarios. However, we discover that camera variation has a significant negative impact on the reliability of Jaccard distance. In particular, Jaccard distance calculates the distance based on the overlap of relevant neighbors. Due to camera variation, intra-camera samples dominate the relevant neighbors, which reduces the reliability of the neighbors by introducing intra-camera negative samples and excluding inter-camera positive samples. To overcome this problem, we propose a novel camera-aware Jaccard (CA-Jaccard) distance that leverages camera information to enhance the reliability of Jaccard distance. Specifically, we design camera-aware k-reciprocal nearest neighbors (CKRNNs) to find k-reciprocal nearest neighbors on the intra-camera and inter-camera ranking lists, which improves the reliability of relevant neighbors and guarantees the contribution of inter-camera samples in the overlap. Moreover, we propose a camera-aware local query expansion (CLQE) to mine reliable samples in relevant neighbors by exploiting camera variation as a strong constraint and assign these samples higher weights in overlap, further improving the reliability. Our CA-Jaccard distance is simple yet effective and can serve as a general distance metric for person re-ID methods with high reliability and low computational cost. Extensive experiments demonstrate the effectiveness of our method.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.10605")
get_code_for_paper("2311.10605")
have("2311.10605")
Connect an agent — have() is free.