MemNet: A Persistent Memory Network for Image Restoration
Citations
2,860 citations
Cites background or methods from "MemNet: A Persistent Memory Network..."
...In addition to the different choice of loss function (L2 in MemNet [25]), we mainly summarize another three differences bwtween MemNet and our RDN....
[...]
...introduced recursive blocks in DRRN [24] and memory block in Memnet [25] for deeper networks....
[...]
...proposed memory block to build MemNet [25]....
[...]
...For BI degradation model, we compare our RDN with 6 state-of-the-art image SR methods: SRCNN [3], LapSRN [13], DRRN [24], SRDenseNet [30], MemNet [25], and MDSR [16]....
[...]
...On the other hand, inspired by MemNet [25], we introduce a 1 × 1 convolutional layer to adaptively control the output information....
[...]
2,298 citations
2,025 citations
Cites background or methods from "MemNet: A Persistent Memory Network..."
...LapSRN [6] MSLapSRN [7] ENet-PAT [8] MemNet [9] EDSR [10] SRMDNF [11] RCAN (ours)...
[...]
...LapSRN [6] MemNet [9] EDSR [10] SRMDNF [11] RCAN 26....
[...]
...We compare our method with 11 state-of-the-art methods: SRCNN [1], FSRCNN [2], SCN [3], VDSR [4], LapSRN [6], MemNet [9], EDSR [10], SRMDNF [11], D-DBPN [16], and RDN [17]....
[...]
...LapSRN [6] MemNet [9] MSLapSRN [7] EDSR [10] RCAN 27....
[...]
...LapSRN [6] MemNet [9] MSLapSRN [7] EDSR [10] RCAN 18....
[...]
1,991 citations
1,430 citations
References
123,388 citations
73,978 citations
42,067 citations
40,257 citations
30,843 citations
"MemNet: A Persistent Memory Network..." refers methods in this paper
...where τ denotes the activation function, including batch normalization [16] followed by ReLU [30], and W i m, i = 1, 2 are the weights of the i-th convolutional layer....
[...]